Skip to main content
Glama

Put an image the user gave you on a carousel slide

flypost_upload_slide_image

Put an image the user gave you on one slide of a template carousel: image_base64 + content_type, or source_url of an image Flypost already hosts (from flypost_attach_post_image or flypost_list_media); max 5MB. The image it replaces stays in the slide's history. Only an image the user actually gave you. To move images between slides use flypost_move_slide_image, flypost_swap_slide_images or flypost_reuse_slide_image.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "content_bank_item_id": "<content_bank_item_id>",
      "slide_id": "<slide_id>"
    },
    "name": "flypost_upload_slide_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
slide_idYesFrom the item's content.slides, or flypost_view_visuals.
file_nameNo
source_urlNoInstead of image_base64: a Flypost-hosted image url.
content_typeNoWith image_base64: MIME type, e.g. image/png.
image_base64NoBase64 image bytes (no data: prefix).
content_bank_item_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this is a non-read-only but non-destructive write, and the description meaningfully supports that by stating the replaced image stays in the slide's history — so overwriting is safe and recoverable. It also discloses a hard behavioral limit (max 5MB) and the accepted input encodings, which are not in the schema. It does not say what happens on an oversize or invalid payload (error vs. truncation) or what the call returns.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the action, then the accepted input formats, then the safety note about slide history, then the alternative tools — a sensible information order with no filler. The user-provided-image constraint is stated twice ('an image the user gave you' and 'Only an image the user actually gave you'), which is mildly redundant but defensible as emphasis on a safety rule.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a write tool with no output schema and a 6-parameter schema, the description covers the decision-critical facts: accepted input forms, size ceiling, what happens to the existing image, and which siblings to use instead. The remaining gap is content_bank_item_id (a required parameter with no explanation anywhere) and the absence of any statement about the response.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With schema coverage at 67%, the description adds real meaning by declaring the mutual exclusivity of the two input routes ('image_base64 + content_type, or source_url') and qualifying source_url as Flypost-hosted only, plus noting base64 carries no data: prefix. However, content_bank_item_id and file_name are left entirely to the schema, so half the meaning is still structured-field-only.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource ('Put an image ... on one slide of a template carousel') and immediately scopes what kind of image is acceptable (user-provided, or a Flypost-hosted source_url). It distinguishes itself from the image-manipulation siblings by naming flypost_move_slide_image, flypost_swap_slide_images and flypost_reuse_slide_image as the tools for repositioning rather than uploading.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives an explicit routing rule for the closest alternatives ('To move images between slides use ...') and tells the agent where a valid source_url comes from (flypost_attach_post_image or flypost_list_media). It also adds a hard usage constraint — only images the user actually supplied. What it does not address is when to prefer flypost_generate_slide_image or flypost_copy_slide_image instead of uploading.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.